© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 20154
    Prev
    Next
    INDEX
    Explanations

    phrases where the concept of something being "an" important or effective element is emphasized

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "an."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bots
    -0.66
     bills
    -0.63
    birds
    -0.63
     majorities
    -0.63
     Regions
    -0.62
    Kids
    -0.62
    reys
    -0.61
    everal
    -0.61
    Gov
    -0.60
    VEN
    -0.60
    POSITIVE LOGITS
    ointed
    1.24
     integral
    1.07
    agram
    1.02
    abolic
    1.00
     indication
    0.98
    onym
    0.98
    oint
    0.96
     obstacle
    0.96
     invitation
    0.95
     example
    0.93
    Activations Density 0.125%

    No Known Activations